Information Gathering as a Resource Bounded Interpretation Task

This paper describes the rationale, architecture, and preliminary implementation of a next generation information gathering system. The goal of this funded research is to exploit the vast amount of information sources available today on the NII including a growing number of digital libraries, independent news agencies, government agencies, as well as human experts providing a variety of services. The large number of information sources and their different levels of accessibility, reliability and associated costs present a complex information gathering coordination problem. We outline the structure and components of a next generation information gathering agent that plans to gather information to support a decision process, reasons about the resource trade-offs of different possible gathering approaches, extracts information from unstructured documents, and uses the extracted information to refine its search and processing